From mboxrd@z Thu Jan  1 00:00:00 1970
Received: from eggs.gnu.org ([2001:4830:134:3::10]:33373)
	by lists.gnu.org with esmtp (Exim 4.71)
	(envelope-from <jasowang@redhat.com>) id 1bEpLz-00043G-IB
	for qemu-devel@nongnu.org; Sun, 19 Jun 2016 22:54:24 -0400
Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71)
	(envelope-from <jasowang@redhat.com>) id 1bEpLv-0002r0-FR
	for qemu-devel@nongnu.org; Sun, 19 Jun 2016 22:54:22 -0400
Received: from mx1.redhat.com ([209.132.183.28]:51393)
	by eggs.gnu.org with esmtp (Exim 4.71)
	(envelope-from <jasowang@redhat.com>) id 1bEpLv-0002qw-9q
	for qemu-devel@nongnu.org; Sun, 19 Jun 2016 22:54:19 -0400
References: <1466245444-24258-1-git-send-email-karahmed@amazon.de>
From: Jason Wang <jasowang@redhat.com>
Message-ID: <57675AD6.6020504@redhat.com>
Date: Mon, 20 Jun 2016 10:54:14 +0800
MIME-Version: 1.0
In-Reply-To: <1466245444-24258-1-git-send-email-karahmed@amazon.de>
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: quoted-printable
Subject: Re: [Qemu-devel] [PATCH] vmxnet3: Fix reading/writing guest memory
 specially when behind an IOMMU
List-Id: <qemu-devel.nongnu.org>
List-Unsubscribe: <https://lists.nongnu.org/mailman/options/qemu-devel>,
	<mailto:qemu-devel-request@nongnu.org?subject=unsubscribe>
List-Archive: <http://lists.nongnu.org/archive/html/qemu-devel/>
List-Post: <mailto:qemu-devel@nongnu.org>
List-Help: <mailto:qemu-devel-request@nongnu.org?subject=help>
List-Subscribe: <https://lists.nongnu.org/mailman/listinfo/qemu-devel>,
	<mailto:qemu-devel-request@nongnu.org?subject=subscribe>
To: KarimAllah Ahmed <karahmed@amazon.de>, qemu-devel@nongnu.org
Cc: Dmitry Fleytman <dmitry@daynix.com>, Anthony Liguori <aliguori@amazon.com>



On 2016=E5=B9=B406=E6=9C=8818=E6=97=A5 18:24, KarimAllah Ahmed wrote:
> When a PCI device lives behind an IOMMU, it should use 'pci_dma_*' fami=
ly of
> functions when any transfer from/to guest memory is required while
> 'cpu_physical_memory_*' family of functions completely bypass any MMU/I=
OMMU in
> the system.
>
> vmxnet3 was exclusively using 'cpu_physical_memory_*' family of functio=
ns which
> works fine with the default QEMU setup where IOMMU is not enabled but f=
ails
> miserably when IOMMU is enabled. This commit converts all such instance=
s in
> favor of 'pci_dma_*'
>
> Cc: Dmitry Fleytman<dmitry@daynix.com>
> Cc: Jason Wang<jasowang@redhat.com>
> Cc:qemu-devel@nongnu.org
> Cc: Anthony Liguori<aliguori@amazon.com>
> Signed-off-by: KarimAllah Ahmed<karahmed@amazon.de>
> ---
>   hw/net/vmware_utils.h  |  55 +++++++------
>   hw/net/vmxnet3.c       | 207 +++++++++++++++++++++++++++-------------=
---------
>   hw/net/vmxnet_tx_pkt.c |  19 ++---
>   hw/net/vmxnet_tx_pkt.h |   8 +-
>   4 files changed, 161 insertions(+), 128 deletions(-)

Thanks for the patch, but could you pls rebase this on top of master?